Link: A Universal Law of Robustness via Isoperimetry | OpenReview This paper purports to explain (and quantify) the observed fact that…
Modified: March 03, 2022.
paper 2015 Existing systems for extracting features ('fingerprints') from molecules look a lot like convnets. They repeatedly apply a hash…
Modified: June 06, 2020.
https://arxiv.org/abs/2106.10314 In Sequential Monte Carlo, we can resample with any set of weights, as long as we then initialize the new…
Modified: June 28, 2021.
Gilmer at al. paper 2017 Experiments on QM9. Unlike SMILES strings, includes molecular geometry . General formulation of message passing…
Modified: March 21, 2022.
Notes from working through Kevin Buzzard's Natural number game (imperial.ac.uk) using the Lean theorem prover. We know from the [ Curry…
Modified: June 09, 2021.
Massive list here: https://github.com/cedrickchee/awesome-bert-nlp Bahdanau, Cho, Bengio. Neural Machine Translation by Jointly Learning to…
Modified: January 24, 2022.
More Is Different (kit.edu) On proof and progress in mathematics (Thurston, 1994) On Being the Right Size (Haldane, 1928))
Modified: March 02, 2022.
Relevant papers: DIfferentiable compositional kernel learning for Gaussian Processes (Sun et al., 2018) Differentiable Architecture Search…
Modified: March 07, 2020.
paper: Chen, Lu, et al. 2021, https://arxiv.org/abs/2106.01345 Trajectories are represented as sequences: where is the return-to-go, i.e…
Modified: April 15, 2022.
Like quantum mechanics! We build up a distribution over variables defined so far. When we need to use a value, we sample from this…
Modified: May 16, 2020.
Christian Naesseth, Fredrik Lindsten, Thomas Schon (2015): http://proceedings.mlr.press/v37/naesseth15.html The main idea: In an SMC…
Modified: July 14, 2021.
https://arxiv.org/abs/1712.02390 Basic idea: optimizers like Adam and RMSProp already keep track of posterior curvature estimates. These are…
Modified: October 30, 2020.
Modified: July 10, 2020.
AI / RL Distributional RL book: https://www.distributional-rl.org/ Alignment Sequences: Value learning: https://www.alignmentforum.org/s…
Modified: June 27, 2023.
A short note on interpreting a transformer layer as performing maximum-likelihood inference in a Gaussian mixture model: https://arxiv.org…
Modified: October 30, 2020.
References: Tegmark and Omohundro, Provably safe systems: the only path to controllable AGI (2023). https://arxiv.org/abs/2309.01933 they…
Modified: September 06, 2023.
In no particular order. Items may move to [ previously read ] if I read them or former reading inbox if I decide I'm not currently…
Modified: August 28, 2023.